Brief Announcement: Byzantine-Tolerant Machine Learning

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of social learning ...

Humans and animals constantly adapt to their environment over the course of their life. This thesis seeks to integrate various timescales of adaptation, ranging from the adaptation of synaptic connections between spiking neurons (milliseconds), rapid behav ...

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

This paper considers the problem of resilient distributed optimization and stochastic learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has its own local cost function. The agents collaborate with ...

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Over the course of a lifetime, the human brain acquires an astonishing amount of semantic knowledge and autobiographical memories, often with an imprinting strong enough to allow detailed information to be recalled many years after the initial learning exp ...

Learning how to reach a reward over long series of actions is a remarkable capability of humans, and potentially guided by multiple parallel learning modules. Current brain imaging of learning modules is limited by (i) simple experimental paradigms, (ii) e ...

This paper addresses the issue of interpretability and auditability of reinforcement-learning agents employed in the recovery of unsecured consumer debt. To this end, we develop a deterministic policy-gradient method that allows for a natural integration o ...

We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment. We propose H-MARL (Hallucinated Multi-Agent Reinforcement Learning), a no ...

Machine learning has become the state of the art for the solution of the diverse inverse problems arising from computer vision and medical imaging, e.g. denoising, super-resolution, de-blurring, reconstruction from scanner data, quantitative magnetic reson ...

Algorithms are everywhere. The recipe for the frangipane cake is an algorithm. If all the listed ingredients are available and the cook is sufficiently deft, after a finite number of small, well-defined steps a delicious dessert will exit the oven. Now, wh ...

This thesis addresses theoretical and practical aspects of identification and subsequent control of self-exciting point processes. The main contributions correspond to four separate scientific papers. In the first paper, we address the challenge of robust ...

The success of deep learning may be attributed in large part to remarkable growth in the size and complexity of deep neural networks. However, present learning systems raise significant efficiency concerns and privacy: (1) currently, training systems are l ...

Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsup ...

The research community of dialog generation has been interested in incorporating emotional information into the design of open-domain dialog systems ever since neural networks (sequence-to-sequence models in particular) were adopted for modeling dialogs. T ...

This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to ...

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

Nowadays, image and video are the data types that consume most of the resources of modern communication channels, both in fixed and wireless networks. Thus, it is vital to compress visual data as much as possible, while maintaining some target quality leve ...

Brief Announcement: Byzantine-Tolerant Machine Learning

Chat with Graph Search

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Learning From Heterogeneous Data Based on Social Interactions Over Graphs

From event-based surprise to lifelong learning. A journey in the timescales of adaptation

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Impact of Redundancy on Resilience in Distributed Optimization and Learning

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Phenomenological theory of variational quantum ground-state preparation

A theory of memory consolidation and synaptic pruning in cortical circuits

Brain signals of a Surprise-Actor-Critic model: Evidence for multiple learning modules in human decision making

Optimal recovery of unsecured debt via interpretable reinforcement learning

Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation

Combining Model Driven and Data Driven Approaches for Inverse Problems in Parameter Estimation and Image Reconstruction: From Modelling to Validation

Practical Byzantine-resilient Stochastic Gradient Descent

Self-Exciting Point Processes: Identification and Control

Algorithms for Efficient and Robust Distributed Deep Learning

Mechanical intelligence for learning embodied sensor-object relationships

Towards Empathetic Open-Domain Chatbots

Network Classifiers Based On Social Learning

Loss landscape and symmetries in Neural Networks

Learning-based Image Coding: Early Solutions Reviewing and Subjective Quality Evaluation